Our publications explore AI systems that reason, plan, and orchestrate agents and tools at scale. This research advances in business-intent understanding, continual adaptation, and governance, showing how AI models become reliable, real-world infrastructure.
INTEGRATED SYSTEMS
PROJECTS
PEOPLE
PATENTS
Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing GRASP, a strategy-aware, multi-stage planning framework.
Workflows that use generative AI are error-prone and hard to audit when model calls, validation, retries, and outputs are scattered across prompts, scripts, and configuration. AI native workflows need these elements connected in one place so the pipeline can be audited and reviewed end to end. This paper
Embodied task planning requires reasoning under uncertainty about world states that are partially observed and incrementally revealed through interaction. However, mostvision–language model (VLM) planners operate in a reactive sense–plan–act loop without maintaining a persistent representation
Timely and accurate assessment of property damage is critical following natural disasters. Traditional on-site inspections are labor-intensive, costly, and often pose safety risks. Advances in satellite imagery and vision-language models (VLMs) enable scalable remote damage assessment; however, integrating
Satellite imagery is vast, high-resolution, and rich with information, but finding specific objects within it using natural language has remained a stubborn challenge. Open-SAT, developed by researchers at NEC Laboratories America and North South University, tackles this problem without retraining any
In satellite applications, user queries often take the form of open-ended natural language, extending beyond a fixed set of predefined categories. This open-vocabulary nature poses significant challenges for retrieving relevant image tiles, as the retrieval system must generalize to a wide range of unseen
Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multiagent plan execution platform that interprets natural-language plans while enforcing stepwise execution through constraints and rubrics.
Deploying microservices across the computing continuum (edgecloud) requires placement decisions that adapt to workload variation and heterogeneous infrastructure, yet existing solutions often rely on static policies or opaque heuristics. We present Bellona a system for reliable and auditable Large
Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical professionals. Despite recent progress in Large Medical Vision-Language Models (Med-VLMs), generating radiology reports that are
Large language models (LLMs) are becoming the centerpiece in the design and deployment of Agentic artificial intelligence (AI) systems. AI agents typically have (a) reasoning ability to analyze and think through the given task, (b) context/memory to remember things in the short-term and long-term, and
Creating effective slide presentations requires adapting both content and structure to match the communication context e.g. whether the presentation is for summarizing to executives, or reporting progress to research supervisors. In research and enterprise environments, this need for context-sensitive
Identifying subject-matter experts within organizations remains a challenging task due to the scale, heterogeneity, and unstructured nature of enterprise knowledge assets. We present TalentScout, an AI-driven expert identification system that constructs a unified, skill-centric knowledge graph by ingesting
Agentic AI systems rely on Large Language Models (LLMs) to execute complex tasks by invoking external functions. The efficiency of these systems depends on how well function execution is managed, especially under heterogeneous and high-variance workloads, where function execution times can range from
Roadside LiDAR (Light Detection and Ranging) sensors promise safer and faster traffic management and vehicular operations. However, occlusion and small view angles are significant challenges to widespread use of roadside LiDARs. We consider fusing data from multiple LiDARs at a traffic intersection to
Enterprises are increasingly adopting Generative AI applications to extract insights from large volumes of multimodal documents in domains such as finance, law, healthcare, and industry. These documents contain structured and unstructured data (images, charts, handwritten texts, etc.) requiring robust
In this paper, we propose a novel agentic AI system called XPF, which enables users to create “agents” using just natural language, where each agent is capable of executing complex, real-world business workflows in an accurate and reliable manner. XPF provides an interface to develop and iterate over
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant
Scene understanding systems analyze visual contexts by detecting objects, their attributes, and the interactions among them to provide a holistic interpretation. Understanding a scene requires analyzing multiple salient regions within a single video frame. Recently, Vision-Language Models (VLMs) have
Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication systems. In this work, we introduce a channel-aware adaptive framework
Latency-critical applications demand quick responses. Ideally, detailed insights are preferable for the best decision making and response actions. However, in situations when detailed insights cannot be provided quickly, even basic information goes a long way in tackling the situation effectively. For
The advancement of Generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), is reshaping the software industry by automating code generation. Many LLM-driven distributed processing systems rely on serial code generation constrained by predefined libraries, limiting flexibility
LiDAR technology has emerged as a pivotal tool in Intelligent Transportation Systems (ITS), providing unique capabilities that have significantly transformed roadside traffic applications. However, this transformation comes with a distinct challenge: the immense volume of data generated by LiDAR sensors.
In Video Analytics Pipelines (VAP), Analytics Units (AUs) such as object detection and face recognition operating on remote servers rely heavily on surveillance cameras to capture high-quality video streams to achieve high accuracy. Modern network cameras offer an array of parameters that directly influence
Communication in Millimeter wave (mmWave) band relies on narrow beams due to directionality, high path loss, and shadowing. One can use beam alignment (BA) techniques to find and adjust the direction of these narrow beams. In this paper, BA at the base station (BS) is considered, where the BS sends a
With the advancement of 5G, edge-assisted video analytics has become increasingly popular, driven by the technologys ability to support low-latency, high-bandwidth applications. However, in scenarios where multiple clients competing for network resources, network contention poses a significant challenge.
Marine litter detection is crucial for environmental monitoring, yet the imbalance in existing datasets limits model performance in identifying various types of waste accurately. This paper presents an efficient data augmentation pipeline that combines generative diffusion models (e.g., Stable Diffusion)
Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particularly multi-modal RAG, can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces (e.g.,
Edge computing has emerged as a transformative technology that reduces application latency, improves cost efficiency, enhances security, and enables large-scale deployment of applications across various domains. In environmental monitoring, systems such as MegaSense[49], use low-cost sensors to gather
Generative artificial intelligence (GenAI), specifically, Large Language Models (LLMs), have shown tremendous potential in automating several tasks and improving human productivity. Recent works have shown them to be quite useful in writing and summarizing text (articles, blogs, poems, stories, songs,
The transformer structure employed in large language models (LLMs), as a specialized category of deep neural networks (DNNs) featuring attention mechanisms, stands out for their ability to identify and highlight the most relevant aspects of input data. Such a capability is particularly beneficial in
Retrieval-augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for understanding of videos is appealing but there are two critical limitations. One-time, upfront conversion of all content
Traffic cameras are essential in urban areas, playing a crucial role in intelligent transportation systems. Multiple cameras at intersections enhance law enforcement capabilities, traffic management, and pedestrian safety. However, efficiently managing and analyzing multi-camera feeds poses challenges
Neural language models for commonsense reasoning often formulate the problem as a QA task and make predictions based on learned representations of language after fine-tuning. However, without providing any fine-tuning data and pre-defined answer candidates, can neural language models still answer commonsense
Costs of LLM API usage rise rapidly when proprietary enterprise data is used as context for user queries to generate more accurate responses from LLMs. To reduce costs, we propose LeanContext, which generates query-aware, compact and AI model-friendly summaries of relevant enterprise data context. This
Resource-constrained hardware such as edge devices or cell phones often rely on cloud servers to provide the required computational resources for inference in deep vision models. However transferring image and video data from an edge or mobile device to a cloud server requires coding to deal with network
Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network bandwidth conditions or storage constraints. However standard video codecs (e.g. H.264) and their rate control modules aim to
Retrieval-augmented generation (RAG) is used in natural language processing (NLP) to provide query-relevant information in enterprise documents to large language models (LLMs). Such enterprise context enables the LLMs to generate more informed and accurate responses. When enterprise data is primarily
Ensuring high-quality video content for wireless users has become increasingly vital. Nevertheless, maintaining a consistent level of video quality faces challenges due to the fluctuating encoded bitrate, primarily caused by dynamic video content, especially in live streaming scenarios. Video compression
AI/ML techniques have been used to solve systems problems, but their applicability to customize solutions on-the-fly has been limited. Traditionally, any customization required manually changing the AI/ML model or modifying the code, configuration parameters, application settings, etc. This incurs too
Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope restrict the applicability of Multi-Modal Large Language Models (MM-LLMs)
Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, widespread LLM integration presents a challenge for small businesses due to the high expenses of LLM API usage. Costs rise rapidly
Providing wireless users with high-quality video content has become increasingly important. However, ensuring consistent video quality poses challenges due to variable encodedbitrate caused by dynamic video content and fluctuating channel bitrate caused by wireless fading effects. Suboptimal selection
For microservices-based real-time stream processing applications, computing at the edge delivers fast responses for low workloads, but as workload increases, the response time starts to slow down due to limited compute capacity. Abundant compute capacity in the cloud delivers fast responses even for
Retrieval augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for combined understanding of multimodal data such as text, images and videos is appealing but two critical limitations exist:
In the evolving Artificial Intelligence (AI) era, the need for real-time algorithm processing in marine edge environments has become a crucial challenge. Data acquisition, analysis, and processing in complex marine situations require sophisticated and highly efficient platforms. This study optimizes
One of the key metrics of interest for stream processing applications is latency, which indicates the total time it takes for the application to process and generate insights from streaming input data. For mission-critical video analytics applications like surveillance and monitoring, it is of paramount
Distributed massive MIMO networks are envisioned to realize cooperative multi-point transmission in next-generation wireless systems. For efficient cooperative hybrid beamforming, the cluster of access points (APs) needs to obtain precise estimates of the uplink channel to perform reliable downlink precoding.
JPEG remains one of the most widespread lossy image coding methods. However, the non-differentiable nature of JPEG restricts the application in deep learning pipelines. Several differentiable approximations of JPEG have recently been proposed to address this issue. This paper conducts a comprehensive
Modern video analytics applications comprise multiple microservices chained together as pipelines and executed on container orchestration platforms like Kubernetes. Kubernetes automatically handles the scaling of these microservices for efficient application execution. There are two popular choices for
Low-complexity estimation and correction of carrier frequency offset (CFO) are essential in orthogonal frequency division multiplexing (OFDM). In this paper, we propose a low overhead blind CFO estimation technique based on cyclic prefix (CP), in multi-input multi-output (MIMO)-OFDM systems. We propose
Deep learning based joint source-channel coding (JSCC) has demonstrated significant advancements in data reconstruction compared to separate source-channel coding (SSCC). This superiority arises from the suboptimality of SSCC when dealing with finite block-length data. Moreover, SSCC falls short in reconstructing
Data crowdsourcing is an increasingly pervasive and lifestyle-changing technology due to the flywheel effect that results from the interaction between the Internet of Things and Cloud Computing. This paper presents the Citizen Science for the Sea with Information Technologies (C4Sea-IT) framework. It
Deep Video Codec Control Lossy video compression is commonly used when transmitting and storing video data. Unified video codecs (e.g., H.264 or H.265) remain the emph(Unknown sysvar: (de facto)) standard, despite the availability of advanced (neural) compression approaches. Transmitting videos in the
In 2008, parallel computing posed significant challenges due to the complexities of parallel programming and the bottlenecks associated with efficient parallel execution. Inspired by the remarkable scalability achieved by networking and storage systems in handling extensive packet traffic and persistent
We present Application in a Box (AnB) product concept aimed at simplifying the deployment and operation of remote 5G applications. AnB comes pre-configured with all necessary hardware and software components, including sensors like cameras, hardware and software components for a local 5G wireless network,
IoT sensors, especially video cameras, are ubiquitously deployed around the world to perform a variety of computer vision tasks in several verticals including retail, health- care, safety and security, transportation, manufacturing, etc. To amortize their high deployment effort and cost, it is desirable
Edge Intelligence has received attention in the recent times for its potential towards improving responsiveness, reducing the cost of data transmission, enhancing security and privacy, and enabling autonomous decisions by edge devices. However, edge devices lack the power and compute resources necessary
Access to high-quality data is an important barrier in the digital analysis of urban settings, including applications within computer vision and urban design. Diverse forms of data collected from sensors in areas of high activity in the urban environment, particularly at street intersections, are valuable
Millimeter‑wave (mmWave) communications is a key enabler towards realizing enhanced Mobile Broadband (eMBB) as a key promise of 5G and beyond, due to the abundance of bandwidth available at mmWave bands. An mmWave coverage map consists of blind spots due to shadowing and fading especially in dense
Time Division Duplex (TDD)-based distributed massive MIMO systems are envisioned as candidate solution for the physical layer of 6G multi-antenna systems supporting cooperative hybrid beamforming that heavily relies on the obtained uplink channel estimates for efficient coherent downlink precoding. However,
Modern applications are designed as an interacting set of microservices, and these applications are typically deployed on container orchestration platforms like Kubernetes. Several attractive features in Kubernetes make it a popular choice for deploying applications, and automatic scaling is one such
Devices with limited computing resources use smaller AI models to achieve low-latency inferencing. However, model accuracy is typically much lower than the accuracy of a bigger model that is trained and deployed in places where the computing resources are relatively abundant. We describe DyCo, a novel
Cameras are increasingly being deployed in cities, enterprises and roads world-wide to enable many applications in public safety, intelligent transportation, retail, healthcare and manufacturing. Often, after initial deployment of the cameras, the environmental conditions and the scenes around these
Serverless edge computing aims to deploy and manage applications so that developers are unaware of challenges associated with dynamic management, sharing, and maintenance of the edge infrastructure. However, this is a non-trivial task because the resource usage by various edge applications varies based
In Video Analytics Pipelines (VAP), Analytics Units (AUs) such as object detection and face recognition running on remote servers critically rely on surveillance cameras to capture high-quality video streams in order to achieve high accuracy. Modern IP cameras come with a large number of camera parameters
Beam search algorithms have been proposed to align the beams from an access point to a user equipment. The process relies on sending beams from a set of scanning beams (SB) and tailoring a transmission beam (TB) using the received feedback. In this paper, we discuss a fundamental trade-off between the
It is a common practice to think of a video as a sequence of images (frames), and re-use deep neural network models that are trained only on images for similar analytics tasks on videos. In this paper, we show that this “leap of faith” that deep learning models that work well on images will also
Roadside LiDAR (Light Detection and Ranging) sensors are recently being explored for intelligent transportation systems aiming at safer and faster traffic management and vehicular operations. A key challenge in such systems is to efficiently transfer massive point-cloud data from the roadside LiDAR devices
5G-LAN is an enterprise local area network (LAN) that leverages 5G technology for wireless connectivity instead of WiFi. 5G technology is unique: it uses network slicing to distinguish customers in the same traffic class using new QoS technologies in the RF domain. This unique ability is not supported
A big challenge in changing a monolithic application into a performant microservices-based application is the design of efficient mechanisms for microservices to communicate with each other. Prior proposals range from custom point-to-point communication among microservices using protocols like gRPC to
The plethora of sensors in our commodity devices provides a rich substrate for sensor-fused tracking. Yet, today’s solutions are unable to deliver robust and high tracking accuracies across multiple agents in practical, everyday environments – a feature central to the future of immersive and collaborative
5G services and applications explicitly reserve compute and network resources in today’s complex and dynamic infrastructure of multi-tiered computing and cellular networking to ensure application-specific service quality metrics, and the infrastructure providers charge the 5G services for the resources
Meta learning algorithms for few-shot video recognition use complex, episodic training but they often fail to learn effective feature representations. In contrast, we propose a new and simpler few-shot video recognition method that does not use meta-learning, but its performance compares well with the
A large number of traffic collisions occur as a result of obstructed sight lines, such that even an advanced driver assistance system would be unable to prevent the crash. Recent work has proposed the use of around-the-corner radar systems to detect vehicles, pedestrians, and other road users in these
Design of multitasking deep learning models has mostly focused on improving the accuracy of the constituent tasks, but the challenges of efficiently deploying such models in a device-edge collaborative setup (that is common in 5G deployments) has not been investigated. Towards this end, in this paper,
Massive MIMO and hybrid beamforming are among the key physical layer technologies for the next generation wireless systems. In the last stage of the hybrid beamforming, the goal is to generate sharp beam with maximal and preferably uniform gain. We highlight the shortcomings of uniform linear arrays
With the growth of 5G, Internet of Things (IoT), edge computing and cloud computing technologies, the infrastructure (compute and network) available to emerging applications (AR/VR, autonomous driving, industry 4.0, etc.) has become quite complex. There are multiple tiers of computing (IoT devices, near
In-band full-duplex (FD) communication has emerged as one of the promising techniques to improve data rates in next generation wireless systems. Typical FD scenarios considered in the literature assume FD base stations (BSs) and half-duplex (HD) users activated either in uplink (UL) or downlink (DL),
A key barrier to building performant, remotely managed and self-optimizing multi-sensor, distributed stream processing edge applications is high programming complexity. We recently proposed DataX [1], a novel platform that improves programmer productivity by enabling easy exchange, transformations, and
To overcome the high pathloss and the intense shadowing in millimeterwave (mmWave) communications, effective beamforming schemes are required which incorporate narrow beams with high beamforming gains. The mm Wave channel consists of a few spatial clusters each associated with an angle of departure (AoD).
In pursuance of the unused spectrum in higher frequencies, millimeter wave (mmWave) bands have a pivotal role. However, the high path loss and poor scattering associated with mmWave communications highlight the necessity of employing effective beamforming techniques. In order to efficiently search for
Millions of cameras at edge are being deployed to power a variety of different deep learning applications. However, the frames captured by these cameras are not always pristine – they can be distorted due to lighting issues, sensor noise, compression etc. Such distortions not only deteriorate visual
Edge computing and 5G have made it possible to perform analytics closer to the source of data and achieve super-low latency response times, which isn’t possible with centralized cloud deployment. In this paper, we present a novel fever screening system, which uses edge machine learning techniques and
Millimeter-wave (mmWave) communications is considered as a key enabler towards the realization of next-generation wireless networks, due to the abundance of available spectrum at mmWave frequencies. However, mmWave suffers from high free-space path-loss and poor scattering resulting in mostly line-of-sight
Microservices-based video analytics pipelines routinely use multiple deep convolutional neural networks. We observe that the best allocation of resources to deep learning engines (or microservices) in a pipeline, and the best configuration of parameters for each engine vary over time, often at a timescale
Applications can tailor a network slice by specifying a variety of QoS attributes related to application-specific performance, function or operation. However, some QoS attributes like guaranteed bandwidth required by the application do vary over time. For example, network bandwidth needs of video streams
Video analytics systems critically rely on video cameras, which capture high quality video frames, to achieve high analytics accuracy. Although modern video cameras often expose tens of configurable parameter settings that can be set by end users, deployment of surveillance cameras today often uses a
We investigate ways to leverage uncertainty in face images to improve the quality of the face clusters. We observe that popular clustering algorithms do not produce better quality clusters when clustering probabilistic face representations that implicitly model uncertainty – these algorithms predict
Applications that use edge computing and 5G to improve response times consume both compute and network resources. However, 5G networks manage only network resources without considering the application’s compute requirements, and container orchestration frameworks manage only compute resources without
The exponential growth in smart sensors and rapid progress in 5G networks is creating a world awash with data streams. However, a key barrier to building performant multi-sensor, distributed stream processing applications is high programming complexity. We propose DataX, a novel platform that improves
Identification of people with elevated body temperature can reduce or dramatically slow down the spread of infectious diseases like COVID-19. We present a novel fever-screening system, F 3 S, that uses edge machine learning techniques to accurately measure core body temperatures of multiple individuals
We design and build SkyHaul, the first large-scale, self-organizing network of Unmanned Aerial Vehicles (UAVs) that are connected using a mm Wave wireless mesh backhaul. While the use of a mmWave backhaul paves the way for a new class of bandwidth-intensive, latency-sensitive cooperative applications
Narrow beams are key to wireless communications in millimeter wave frequency bands. Beam alignment (BA) allows the base station (BS) to adjust the direction and width of the beam used for communication. During BA, the BS transmits a number of scanning beams covering different angular regions. The goal
mmWave 5G networks promise to enable a new generation of networked applications requiring a combination of high throughput and ultra-low latency. However, in practice, mmWave performance scales poorly for large numbers of users due to the significant overhead required to manage the highly-directional
Centralized cloud computing with 100+ milliseconds network latencies cannot meet the tens of milliseconds to sub-millisecond response times required for emerging 5G applications like autonomous driving, smart manufacturing, tactile internet, and augmented or virtual reality. We describe a new, dynamic
Directional transmission patterns (a.k.a. narrow beams) are the key to wireless communications in millimeter wave (mmWave) frequency bands which suffer from high path loss, severe shadowing, and intense blockage. In addition, the propagation channel in mmWave frequencies incorporates only a few number
The recent innovation of frequency-shifted (FS) backscatter allows for backscattering with commodity devices, which are inherently half-duplex. However, their reliance on oscillators for generating the frequency-shifting signal on the tag, forces them to incur the transient phase of the oscillator before
Retailers are aiming to enhance customer experience by automating the checkout process. The key impediment here is the effort to manually align the product barcode with the scanner, requiring sequential handling of items without blocking the line-of-sight of the laser beam. While recent systems such
RFID applications for taking inventory and processing transactions in point-of-sale (POS) systems improve operational efficiency but are not designed to provide insights about customers’ interactions with products. We bridge this gap by solving the proximity grouping problem to identify groups of RFID
Directional transmission patterns (a.k.a. narrow beams) are the key to wireless communications in millimeter wave (mmWave) frequency bands which suffer from high path loss and severe shadowing. In addition, the propagation channel in mmWave frequencies incorporates only a few number of spatial clusters
Millimeter-wave (mmWave) bands have the potential to enable significantly high data rates in wireless systems. In order to overcome intense path loss and severe shadowing in these bands, it is essential to employ directional beams for data transmission. Furthermore, it is known that the mmWave channel
In-band full-duplex (FD) communications – enabled by recent advances in antenna and RF circuit design – has emerged as one of the promising techniques to improve data rates in wireless systems. One of the major roadblocks in enabling high data rates in FD systems is the inter-user interference (IUI)
Millimeter-wave (mmWave) bands have shown the potential to enable high data rates for next generation mobile networks. In order to cope with high path loss and severe shadowing in mmWave frequencies, it is essential to employ massive antenna arrays and generate narrow transmission patterns (beams). When
First responders, a critical lifeline of any society, often find themselves in precarious situations. The ability to track them in real-time in unknown indoor environments would significantly contribute to the success of their mission as well as their safety. In this work, we present the design, implementation
We envision a flexible, dynamic airborne LTE infrastructure built upon Unmanned Autonomous Vehicles (UAVs) that will provide on-demand, on-time, network access, anywhere. In this paper, we design, implement and evaluate SkyRAN, a self-organizing UAV-based LTE RAN (Radio Access Network) that is a key
The advances in unmanned aerial vehicle (UAV) technology have empowered mobile operators to deploy LTE base stations (BSs) on UAVs, and provide on-demand, adaptive connectivity to hotspot venues as well as emergency scenarios. However, today’s evolved packet core (EPC) that orchestrates the LTE RAN faces
The advent of LTE into the unlicensed spectrum has necessitated the understanding of its operational efficiency when sharing spectrum with different radio access technologies. Our study reveals that LTE, owing to its inherent transmission characteristics, suffers significant performance degradation in
Un-manned aerial vehicle (UAVs) have the potential to change the landscape of wide-area wireless connectivity by bringing them to areas where connectivity was sparing or non-existent (e.g. rural areas) or has been compromised due to disasters. While Google’s Project Loon and Facebook’s Project Aquila